Liking cljdoc? Tell your friends :D

clj-xref.bench

LLM token savings benchmark.

Compares whole-tree vs xref-guided context selection by asking Claude the same questions under both strategies and measuring token usage and answer correctness.

Requires clj-http and cheshire on the classpath (available via :dev profile).

LLM token savings benchmark.

Compares whole-tree vs xref-guided context selection by asking Claude
the same questions under both strategies and measuring token usage
and answer correctness.

Requires clj-http and cheshire on the classpath (available via :dev profile).
raw docstring

(print-results results)

Print a comparison table.

Print a comparison table.
sourceraw docstring

run-benchmarkclj

(run-benchmark {:keys [paths model questions]
                :or {paths ["src"] questions test-questions}})

Run the full benchmark. Returns vector of result maps. Options: :paths - source paths to analyze (default ["src"]) :model - Claude model (default haiku) :questions - override test questions

Run the full benchmark. Returns vector of result maps.
Options:
  :paths     - source paths to analyze (default ["src"])
  :model     - Claude model (default haiku)
  :questions - override test questions
sourceraw docstring

test-questionsclj

source

whole-tree-contextclj

(whole-tree-context paths)

Build context from all source files under paths.

Build context from all source files under paths.
sourceraw docstring

xref-guided-contextclj

(xref-guided-context db sym paths)

Build context from only the files in sym's xref neighborhood.

Build context from only the files in sym's xref neighborhood.
sourceraw docstring

cljdoc builds & hosts documentation for Clojure/Script libraries

Keyboard shortcuts
Ctrl+kJump to recent docs
Move to previous article
Move to next article
Ctrl+/Jump to the search field
× close